Autonomous Driving Path Updates Using Curvature-Based Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current advanced driver assistance systems (ADAS) face challenges in optimizing user convenience and safety during autonomous driving, particularly in effectively transmitting and updating electronic Horizon data to ensure accurate and dynamic path planning.
Innovation Solution
A path providing device and method that utilize a communication unit, interface unit, and processor to receive map information, sensing data from various sensors, and generate autonomous driving visibility information, dynamically updating the optimal path based on movable objects and sensor data fusion, tailored to specific sensor ranges and driving conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple sensors are used to gather comprehensive sensing information for autonomous driving, then the accuracy and reliability of path planning is improved, but the device complexity and computational burden increase
Solution Approach 1:
The patent segments the sensing information processing by dividing the road area into multiple sections based on curvature characteristics. Different sensor data fusion strategies are applied to different sections: high-curvature sections use data from all sensors, while low-curvature sections use limited sensor data. This segmentation resolves the contradiction by reducing computational complexity in areas where full sensor processing is not necessary, while maintaining high reliability in critical high-curvature sections.
Solution Approach 2:
The patent applies local quality by adjusting the level of sensor data processing based on local road characteristics. In high-curvature sections where path planning accuracy is critical, all sensor data is processed comprehensively. In straight or low-curvature sections, only essential sensor data is processed. This local differentiation maintains high reliability where needed while reducing overall device complexity and computational burden.
2Loss of information
If sensor data from all sensors is processed to update autonomous driving visibility information, then the completeness of path information is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent segments the road path into multiple sections based on curvature characteristics and applies different data processing levels to each section. High-curvature sections receive comprehensive sensor data processing to ensure complete visibility information, while low-curvature sections receive minimal processing. This segmentation reduces overall processing time while maintaining information completeness in critical areas.
Solution Approach 2:
The patent implements partial action by processing sensor data selectively rather than uniformly across all road sections. Only the necessary portion of sensor data is processed for each section based on its curvature characteristics. This approach maintains sufficient visibility information completeness for safe autonomous driving while significantly reducing computational time and resource consumption.
3Adaptability or versatility
If the system adapts to different driving conditions and sensor ranges, then the versatility and safety of autonomous driving is improved, but the control complexity increases
Solution Approach 1:
The patent implements dynamics by making the sensor selection and data processing strategy adaptive to real-time driving conditions. The system dynamically adjusts which sensors are activated and how their data is processed based on factors such as road curvature, vehicle speed, and environmental conditions. This dynamic adaptation improves versatility and safety across different driving scenarios while avoiding the complexity of a static system that must handle all possible conditions with maximum complexity.
Data Source
AI summary
A path providing device configured to provide a path information to a vehicle includes a communication unit configured to receive, from a server, map information including a plurality of layers of data, an interface unit configured to receive sensing information from one or more sensors disposed at the vehicle, and a processor. The processor is configured to determine an optimal path for guiding the vehicle from an identified lane, generate autonomous driving visibility information based on the sensing information and the determined optimal path, update the optimal path based on dynamic information related to a movable object located on the optimal path and the autonomous driving visibility information, receive different types of sensor data from a plurality of sensors, and update at least one of the autonomous driving visibility information or the optimal path based on information generated by combining at least two types of sensor data.